Sampling from a Log-Concave Distribution with Projected Langevin Monte Carlo

Author:

Bubeck Sébastien,Eldan RonenORCID,Lehec Joseph

Publisher

Springer Science and Business Media LLC

Subject

Computational Theory and Mathematics,Discrete Mathematics and Combinatorics,Geometry and Topology,Theoretical Computer Science

Reference19 articles.

1. Ahn, S., Korattikara, A., Welling, M.: Bayesian posterior sampling via stochastic gradient Fisher scoring. In: Proceedings of the 29th International Conference on Machine Learning (ICML’12), pp. 782–846. IMLS (2012)

2. Bach, F., Moulines, E.: Non-strongly-convex smooth stochastic approximation with convergence rate $${{\rm O}}(1/n)$$ O ( 1 / n ) . In: Proceedings of the 26th International Conference on Neural Information Processing Systems (NIPS’13), vol. 1, pp. 773–781. Curran Associates (2013)

3. Cousins, B., Vempala, S.: Bypassing KLS: Gaussian cooling and an $${{\rm O}}^*(n^3)$$ O ∗ ( n 3 ) volume algorithm. In: Proceedings of the 47th Annual ACM Symposium on Theory of Computing (STOC’15), pp. 539–548. ACM, New York (2015)

4. Dalalyan, A.S.: Theoretical guarantees for approximate sampling from a smooth and log-concave densities. J. R. Stat. Soc. Stat. Methodol. Ser. B. https://doi.org/10.1111/rssb.12183

5. Dyer, M., Frieze, A., Kannan, R.: A random polynomial-time algorithm for approximating the volume of convex bodies. J. Assoc. Comput. Mach. 38(1), 1–17 (1991)

Cited by 25 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Convergence error analysis of reflected gradient Langevin dynamics for non-convex constrained optimization;Japan Journal of Industrial and Applied Mathematics;2024-08-20

2. On the Privacy of Noisy Stochastic Gradient Descent for Convex Optimization;SIAM Journal on Computing;2024-07-19

3. Emerging Directions in Bayesian Computation;Statistical Science;2024-02-01

4. SARA: Slot Attention for Robust Adversarial Training;2023 6th International Conference on Algorithms, Computing and Artificial Intelligence;2023-12-22

5. The Langevin Monte Carlo algorithm in the non-smooth log-concave case;The Annals of Applied Probability;2023-12-01

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3